Mapping attractor fields in face space: the atypicality bias in face recognition

A familiar face can be recognized across many changes in the stimulus input. In this research, the many-to-one mapping of face stimuli to a single face memory is referred to as a face memoryʹs `attractor fieldʹ. According to the attractor field approach, a face memory will be activated by any stimuli falling within the boundaries of its attractor field. It was predicted that by virtue of its location in a multi-dimensional face space, the attractor field of an atypical face will be larger than the attractor field of a typical face. To test this prediction, subjects make likeness judgments to morphed faces that contained a 50/50 contribution from an atypical and a typical parent face. The main result of four experiments was that the morph face was judged to bear a stronger resemblance to the atypical face parent than the typical face parent. The computational basis of the atypicality bias was demonstrated in a neural network simulation where morph inputs of atypical and typical representations elicited stronger activation of atypical output units than of typical output units. Together, the behavioral and simulation evidence supports the view that the attractor fields of atypical faces span over a broader region of face space that the attractor fields of typical faces.